{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:3TYWLHKVLAOTW5QS5L7ZFKPTIO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b8bca7a6f5e70494b71cad9de0633f78f6a89da3e9e3d92e5131e2411b823600","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-01T21:14:39Z","title_canon_sha256":"dae933757c4980ba50e18989ba6deb833eca6351bad9db74917011cfe9a502fd"},"schema_version":"1.0","source":{"id":"1207.0246","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.0246","created_at":"2026-05-18T00:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"1207.0246v4","created_at":"2026-05-18T00:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.0246","created_at":"2026-05-18T00:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"3TYWLHKVLAOT","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"3TYWLHKVLAOTW5QS","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"3TYWLHKV","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:c1e7a1be319b98c021508b28036488522ae78447cac5d0ffe91d7bb31c73e7ec","target":"graph","created_at":"2026-05-18T00:49:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Web Data Extraction is an important problem that has been studied by means of different scientific tools and in a broad range of applications. Many approaches to extracting data from the Web have been designed to solve specific problems and operate in ad-hoc domains. Other approaches, instead, heavily reuse techniques and algorithms developed in the field of Information Extraction.\n  This survey aims at providing a structured and comprehensive overview of the literature in the field of Web Data Extraction. We provided a simple classification framework in which existing Web Data Extraction appl","authors_text":"Emilio Ferrara, Giacomo Fiumara, Pasquale De Meo, Robert Baumgartner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-01T21:14:39Z","title":"Web Data Extraction, Applications and Techniques: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.0246","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e5f9a669e2d3e16bbad3e337c9a55df7db2f308500e99b31c6c469441c725df","target":"record","created_at":"2026-05-18T00:49:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b8bca7a6f5e70494b71cad9de0633f78f6a89da3e9e3d92e5131e2411b823600","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-01T21:14:39Z","title_canon_sha256":"dae933757c4980ba50e18989ba6deb833eca6351bad9db74917011cfe9a502fd"},"schema_version":"1.0","source":{"id":"1207.0246","kind":"arxiv","version":4}},"canonical_sha256":"dcf1659d55581d3b7612eaff92a9f3439e229c924aee17a089a00e886e3f2054","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcf1659d55581d3b7612eaff92a9f3439e229c924aee17a089a00e886e3f2054","first_computed_at":"2026-05-18T00:49:35.450138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:35.450138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uRgVu2M3xvBkuHkDDOqMs5qJ7CLZ1NRb4xkgQFob588V0axZkPl9EyKaMwhcaQBQ+Ofq1WQ/qYSsYOF2gmVABA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:35.450675Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.0246","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e5f9a669e2d3e16bbad3e337c9a55df7db2f308500e99b31c6c469441c725df","sha256:c1e7a1be319b98c021508b28036488522ae78447cac5d0ffe91d7bb31c73e7ec"],"state_sha256":"51c5e8231dd2cf3d1c0889113e1761ba97264fa888190f67f46d31cf31b089c3"}